Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs
This work addresses a domain-specific problem in natural language processing for researchers and practitioners in relation extraction, focusing on handling long-tailed relations and noise, but it is incremental as it builds on existing denoising approaches.
The paper tackles the challenges of label noise and long-tailed distributions in distantly supervised relation extraction by introducing a constraint graph-based framework (CGRE) that uses graph convolution networks to propagate information from data-rich to data-poor relations, achieving significant improvements over previous methods.
Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In this paper, we introduce a constraint graph to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Extensive experimental results indicate that CGRE achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction. The pre-processed datasets and source code are publicly available at https://github.com/tmliang/CGRE.